osobhandClaude Opus 5.5
e38f9123db
h5py's built-in compression="lzf" failed with UnsupportedFilter(32000). The new `lzf` feature (no dependencies, on by default in clawhdf5-format and the facade) decodes the raw liblzf stream h5py's filter stores, bounded by the chunk size, and encodes it: DatasetBuilder::with_lzf() (or with_plugin_filter(PluginFilter::Lzf)) writes the filter with h5py's cd_values (filter version 4, liblzf 0x0105, chunk size in bytes), flagged optional as h5py does. ChunkOptions gains a `plugin` field for the plugin filters; build_pipeline_for_chunk passes the chunk size to filters that record it. tests/plugin_filters_interop.rs: h5py writes LZF (alone, with shuffle, with shuffle+fletcher32) over 12 dtype/shape/chunk/data cases with partial edge chunks and incompressible data, and every dataset reads byte for byte equal to its unfiltered twin; our LZF output (1-D and 2-D, edge chunks, with and without shuffle) reads back in h5py. Both fail with the decoder removed. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
67 lines
2.4 KiB
TOML
67 lines
2.4 KiB
TOML
[package]
|
|
name = "clawhdf5-format"
|
|
version = "2.7.0"
|
|
edition = "2024"
|
|
rust-version.workspace = true
|
|
description = "Pure-Rust HDF5 binary format parsing and writing — no C dependencies"
|
|
license = "MIT"
|
|
repository = "https://git.redclaw.dev/quantumclaw/clawhdf5"
|
|
readme = "README.md"
|
|
keywords = ["hdf5", "science", "data", "binary", "no-std"]
|
|
categories = ["parser-implementations", "science", "encoding", "no-std"]
|
|
|
|
[dependencies]
|
|
byteorder = { version = "1", default-features = false }
|
|
portable-atomic = { version = "1" }
|
|
flate2 = { version = "1", default-features = false, features = ["rust_backend"], optional = true }
|
|
sha2 = { version = "0.10", default-features = false, optional = true }
|
|
rayon = { version = "1", optional = true }
|
|
crc32fast = { version = "1", optional = true }
|
|
lz4_flex = { version = "0.11", optional = true }
|
|
zstd = { version = "0.13", optional = true }
|
|
blake3 = { version = "1", optional = true }
|
|
libaec-sys = { path = "../libaec-sys", version = "0.1", optional = true }
|
|
pco = { version = "1.0", optional = true }
|
|
|
|
[dev-dependencies]
|
|
half = { workspace = true }
|
|
serde_json = "1"
|
|
criterion = { workspace = true }
|
|
clawhdf5-derive = { path = "../clawhdf5-derive", version = "2.7.0" }
|
|
|
|
[[bench]]
|
|
name = "bench"
|
|
harness = false
|
|
|
|
[features]
|
|
# Deflate backend: `zlib-rs` (pure Rust) by default. `fast-deflate` selects
|
|
# zlib-ng instead (C, built with cmake); flate2 prefers a C zlib whenever one
|
|
# is enabled, so turning it on anywhere in the build overrides the default.
|
|
default = ["std", "checksum", "deflate", "provenance", "zlib-rs", "system-zlib-decompress", "lzf"]
|
|
std = []
|
|
checksum = []
|
|
deflate = ["flate2"]
|
|
provenance = ["sha2"]
|
|
parallel = ["rayon", "std"]
|
|
fast-checksum = ["crc32fast"]
|
|
fast-deflate = ["flate2/zlib-ng"]
|
|
system-zlib = ["flate2/zlib-default"]
|
|
system-zlib-decompress = []
|
|
# `runtime_detection` gives zlib-rs `std`, which it needs to detect and use
|
|
# SIMD at runtime. flate2 enables it by default, but we build flate2 with
|
|
# default-features = false, and without it zlib-rs inflates 3.5x slower.
|
|
zlib-rs = ["flate2/zlib-rs", "flate2/runtime_detection"]
|
|
lz4 = ["lz4_flex"]
|
|
zstd = ["dep:zstd"]
|
|
blake3_hash = ["blake3"]
|
|
szip = ["libaec-sys"]
|
|
pcodec = ["dep:pco"]
|
|
# Plugin filters, pure Rust. LZF (32000) is h5py's built-in compression; it
|
|
# has no dependencies, so it is on by default.
|
|
lzf = []
|
|
|
|
[[bench]]
|
|
name = "parallel_decompress_bench"
|
|
harness = false
|
|
required-features = ["parallel"]
|